新闻

LFM2.5-Encoders for Fast Long-Context Inference on CPU

Hugging Face · 发布于 2026年7月28日 · 阅读约3分钟

30秒读懂

发生了什么: Liquid AI released two encoder models, LFM2.5-Encoder-230M and 350M, optimized for fast CPU inference on documents up to 8,192 tokens.
为何重要: Engineers building classification, routing, or extraction systems that run continuously on existing hardware and need to process long documents cheaply.
注意: Benchmarks use PyTorch eager mode on unspecified CPU hardware. No ONNX or quantized exports yet, limiting production deployment options for high-volume serving.

收听本摘要

文章节选

Back to Articles

a]:hidden">

LFM2.5-Encoders for Fast Long-Context Inference on CPU

Team Article Published July 28, 2026

Upvote 45

+39

Fernando Fernandes Neto fernandofernandes Follow

LiquidAI

Edoardo Mosca EdoardoMosca Follow

LiquidAI

Maxime Labonne mlabonne Follow

LiquidAI

Leonie Monigatti iamleonie Follow

LiquidAI

Today, we release two new encoder models on Hugging Face: LFM2.5-Encoder-230M and LFM2.5-Encoder-350M . They match the quality of larger models but stay fast as inputs get longer. This means you can run document-scale jobs on the hardware you already have, even on CPU.

Here's what you get:

Strong for their size: match or beat larger encoders on GLUE, SuperGLUE, and multilingual tasks.

8,192-token context with latency that grows slowly as inputs get longer.

Fast on CPU : about 3.7× faster than ModernBERT-base at long context.

With these, you can build intent routers, policy linters, PII detectors, and text classifiers that run cheaply, all day. See the live demos below.

Why we built a general-purpose encoder

Last month we released LFM2.5-Retrievers , built for multilingual search. LFM2.5-Encoders come from the same family but serve a broader purpose. They're pre-trained with a masked-language objective, so you can fine-tune them for classification, token-level tasks, and search alike. Search is just one thing an encoder enables. That's why we bu

节选自原文。请前往来源阅读全文。

阅读完整文章

inference

The Agent Architect

每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。

每周一封邮件,一键退订。您的地址仅用于发送简报。

LFM2.5-Encoders for Fast Long-Context Inference on CPU

Hugging Face · 发布于 2026年7月28日 · 阅读约3分钟

30秒读懂

发生了什么: Liquid AI released two encoder models, LFM2.5-Encoder-230M and 350M, optimized for fast CPU inference on documents up to 8,192 tokens.
为何重要: Engineers building classification, routing, or extraction systems that run continuously on existing hardware and need to process long documents cheaply.
注意: Benchmarks use PyTorch eager mode on unspecified CPU hardware. No ONNX or quantized exports yet, limiting production deployment options for high-volume serving.

收听本摘要

文章节选

Back to Articles

a]:hidden">

LFM2.5-Encoders for Fast Long-Context Inference on CPU

Team Article Published July 28, 2026

Upvote 45

+39

Fernando Fernandes Neto fernandofernandes Follow

LiquidAI

Edoardo Mosca EdoardoMosca Follow

LiquidAI

Maxime Labonne mlabonne Follow

LiquidAI

Leonie Monigatti iamleonie Follow

LiquidAI

Here's what you get:

Strong for their size: match or beat larger encoders on GLUE, SuperGLUE, and multilingual tasks.

8,192-token context with latency that grows slowly as inputs get longer.

Fast on CPU : about 3.7× faster than ModernBERT-base at long context.

With these, you can build intent routers, policy linters, PII detectors, and text classifiers that run cheaply, all day. See the live demos below.

Why we built a general-purpose encoder

节选自原文。请前往来源阅读全文。

inference

The Agent Architect

每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。

每周一封邮件,一键退订。您的地址仅用于发送简报。